Havuz

Open-source desktop AI agent that gets work done — plans & self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in

Native Safari browser automation for AI agents. 98 tools via AppleScript — zero overhead, keeps logins, runs silently in background. Drop-in

One chat, unlimited AI orchestration.

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

The full featured self-hosted Codex gateway, for teams, agents and you

Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI appli

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs

Sanitized Origin Pro MCP skill package with bilingual documentation

An 8M-parameter English text-to-speech model distilled from Kokoro-82M. 9 MB, runs 18x real time on one CPU thread.

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVID

122 个逆向工程 AI 技能：恶意软件分析 / 软件逆向 / 固件嵌入式 / 协议逆向 / 移动应用 / 脱壳反混淆 / 软件破解 / 漏洞挖掘 / 托管代码 / 取证情报 / CTF。

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Clau

Static analysis for the debt AI agents leave in PHP: 34 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectat

CDAF (Cached Descriptive Asset Files) - open sidecar format for video so AI agents stop re-analyzing the same footage. Spec, CLI, agent skil

Searchable football data provider documentation for AI coding agents. Like Context7 for football data.

Mirror the official Claude desktop app installers (macOS universal DMG, Windows x64/arm64 MSIX) into GitHub Releases + Cloudflare R2 short l

Reusable AI prompt and project brief system for cinematic scroll-driven 2.5D websites.

Go implementation of AI coding agent

A front-end UI for ComfyUI made for beginner level users.

24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demo

小红书封面生成器 - Claude Code Skill，支持18种预设风格，命令行直接生成小红书封面

25 fixed illustration styles for Codex: 9 skills, prompt recipes, and visual references

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.

AI Developer for Unreal Engine — An autonomous AI agent that creates Blueprints, C++, levels, materials, widgets, and more inside the UE5 ed

JoyCode API 代理 — 协议翻译成 Anthropic/OpenAI 兼容格式，让 Claude Code 直接调用 JoyCode支持的模型，比如GLM 5.1等

One local board for Claude Code, Codex, Cursor and 5 more coding agents. See which session needs you, share your fleet card, start free on $

Local, open-source (Apache 2.0) voice layer for Claude Code and Codex on macOS that reads your coding agent's progress aloud. Kokoro text-to

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

基于 SpringAI 的 Agent 开发项目：一个面向“组织知识库 + AI 助手”的 RAG Agent实战项目，把权限隔离、文档入库、混合检索、证据约束、Agent 工具调用和 Docker 部署串成了一条完整工程链路。如果你正在找一个能写进简历、能讲清架构、能覆盖 Sp

Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routin

The execution control plane for AI agents. Govern every model request, MCP tool call, A2A delegation, and downstream action—while keeping yo

An Self-Evolving Stock Strategy Research Agent 策略回测和自我进化

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus vers

CAD CLI and MCP server for AI agents

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share s

把普通文本变成以假乱真的手写体图片：手写字体 + 信纸背景 + 字距/行距/笔画随机扰动。GUI（PyQt6）与 CLI 双入口，numpy/scipy 高性能渲染引擎。

A minimal, readable reference implementation of the Operational Ontology pattern. Palantir Foundry is one implementation; this is the concep

Think Claude Code's auto mode but for pi (and oh-my-pi). Selectable model, sensible defaults.

High performance multithreaded task execution and optimization engine for agents and dweb apps

OryxOS is an open-source Distributed AI Agent OS

Open-source C++17 engine for backtesting and forward execution, with a versioned C ABI; Pine Script v6 runs through code generation. Against

Agent-first AI SEO (AEO/GEO) operating platform

Agent 通用长期记忆层：Agent 将重要信息按类型记录为多篇可读的 markdown 记忆文档，文档以链接形式列在限长索引中，索引随会话自动注入。DeepSeek Harness（dsh）有专用插件 dsh-engramory。

DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub

This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.

MindSpark - Mind Map for Everyone